MAP-SNN: Mapping Spike Activities with Multiplicity, Adaptability, and Plasticity into Bio-Plausible Spiking Neural Networks

TL;DR

This paper introduces MAP-SNN, a bio-plausible spiking neural network model that incorporates multiplicity, adaptability, and plasticity to improve robustness, efficiency, and temporal feature extraction, achieving competitive results on neuromorphic datasets.

Contribution

It proposes a novel MAP framework integrating multiple spike patterns, spike frequency adaptation, and trainable synapses for enhanced bio-interpretability and performance in SNNs.

Findings

Achieves competitive performance on N-MNIST and SHD datasets.

Demonstrates improved robustness, efficiency, and temporal feature extraction.

Validates the significance of MAP properties in SNNs.

Abstract

Spiking Neural Network (SNN) is considered more biologically realistic and power-efficient as it imitates the fundamental mechanism of the human brain. Recently, backpropagation (BP) based SNN learning algorithms that utilize deep learning frameworks have achieved good performance. However, bio-interpretability is partially neglected in those BP-based algorithms. Toward bio-plausible BP-based SNNs, we consider three properties in modeling spike activities: Multiplicity, Adaptability, and Plasticity (MAP). In terms of multiplicity, we propose a Multiple-Spike Pattern (MSP) with multiple spike transmission to strengthen model robustness in discrete time-iteration. To realize adaptability, we adopt Spike Frequency Adaption (SFA) under MSP to decrease spike activities for improved efficiency. For plasticity, we propose a trainable convolutional synapse that models spike response current to enhance the diversity of spiking neurons for temporal feature extraction. The proposed SNN model achieves competitive performances on neuromorphic datasets: N-MNIST and SHD. Furthermore, experimental results demonstrate that the proposed three aspects are significant to iterative robustness, spike efficiency, and temporal feature extraction capability of spike activities. In summary, this work proposes a feasible scheme for bio-inspired spike activities with MAP, offering a new neuromorphic perspective to embed biological characteristics into spiking neural networks.